yolo

Run detection

$ yolo detect predict model=[yolov8n.pt] source=[image.jpg]

$ yolo train data=[data.yaml] model=[yolov8n.pt] epochs=[100]

$ yolo val model=[best.pt]

$ yolo export model=[best.pt] format=[onnx]

$ yolo track source=[video.mp4] model=[yolov8n.pt]

yolo task mode [options]

yolo is the CLI for Ultralytics YOLOv8, a state-of-the-art computer vision framework. It provides commands for object detection, instance segmentation, and image classification tasks from the terminal.
The tool supports a complete workflow: train builds models from datasets, val evaluates model accuracy, predict runs inference on images or video, and export converts models to deployment formats like ONNX and TensorRT. The track mode performs multi-object tracking on video streams.
Each command accepts a task type (detect, segment, classify) and a mode. Pre-trained models can be used directly for inference, or fine-tuned on custom datasets. GPU acceleration is supported through PyTorch for real-time performance.

detect

Object detection.

Segmentation.

Classification.

Run inference.

Train model.

Validate model.

Export format.

Python/PyTorch required. GPU recommended. Model download.

yolo CLI is part of Ultralytics, providing the YOLOv8 object detection and computer vision toolkit.

python(1), pytorch(1)